Dictionary editing apparatus, dictionary editing method, and recording medium recording thereon dictionary editing program

Abstract

According to one embodiment, a dictionary editing apparatus includes a processor with hardware. The processor extracts a word from text data. The processor appends a character pronunciation to the extracted word. The processor calculates at least one of a first reliability denoting a reliability of the extracted word and a second reliability denoting a reliability of the appended character pronunciation. The processor specifies a word to be a modification candidate in accordance with the first reliability. The processor specifies a character pronunciation to be a modification candidate in accordance with the second reliability.

The invention claimed is: 
     
       1. A dictionary editing apparatus comprising a processor with hardware, the processor being configured to:
 extract a word from text data; 
 append a character pronunciation to the extracted word; 
 calculate a first reliability denoting a reliability of the extracted word based on scores of morphemes obtained by morpheme analysis and a second reliability denoting a reliability of the appended character pronunciation based on a score obtained in accordance with a character pronunciation appendage; 
 specify a word to be a modification candidate in accordance with the first reliability; and 
 specify a character pronunciation to be a modification candidate in accordance with the second reliability, 
 wherein the processor calculates the first reliability according to whether the extraction of the word has been performed based on a character string with a line feed by connecting characters before and after the line feed in the text data. 
 
     
     
       2. The dictionary editing apparatus according to  claim 1 , wherein the processor calculates the first reliability using information on a word that exists on a periphery of the extracted word in the text data. 
     
     
       3. The dictionary editing apparatus according to  claim 1 , wherein the processor calculates the second reliability using at least one of: whether the character pronunciation has been appended based on a word registered in a dictionary for performing character pronunciation appendage; whether the character pronunciation has been appended based on multiple words registered in the dictionary; or whether the word to which the character pronunciation has been appended includes a numerical or alphabetical character. 
     
     
       4. The dictionary editing apparatus according to  claim 1 , wherein the processor displays, on a display, the extracted word and character pronunciation to the extracted word, and highlights the specified word or character pronunciation to be a modification candidate. 
     
     
       5. The dictionary editing apparatus according to  claim 4 , wherein the processor performs the highlighting by changing at least one of: a background color of a cell in which a word or character pronunciation to be the modification candidate is displayed; a thickness of a frame of the cell; a size of the frame of the cell; a color of the frame of the cell; a color of characters displayed in the cell; a font of the characters; or a size of the characters. 
     
     
       6. A dictionary editing method, comprising:
 extracting a word from text data; 
 appending a character pronunciation to the extracted word; 
 calculating a first reliability denoting a reliability of the extracted word based on scores of morphemes obtained by morpheme analysis and a second reliability denoting a reliability of the appended character pronunciation based on a score obtained in accordance with a character pronunciation appendage; 
 specifying a word to be a modification candidate in accordance with the first reliability; and 
 specifying a character pronunciation to be a modification candidate in accordance with the second reliability, 
 wherein the first reliability is calculated according to whether the extraction of the word has been performed based on a character string with a line feed by connecting characters before and after the line feed in the text data. 
 
     
     
       7. A computer-readable, non-transitory recording medium recording thereon a dictionary editing program for causing a processor to execute:
 extracting a word from text data; 
 appending a character pronunciation to the extracted word; 
 calculating a first reliability denoting a reliability of the extracted word based on scores of morphemes obtained by morpheme analysis and a second reliability denoting a reliability of the appended character pronunciation based on a score obtained in accordance with a character pronunciation appendage; 
 specifying a word to be a modification candidate in accordance with the first reliability; and 
 specifying a character pronunciation to be a modification candidate in accordance with the second reliability, 
 wherein the first reliability is calculated according to whether the extraction of the word has been performed based on a character string with a line feed by connecting characters before and after the line feed in the text data.